Total relevant papers: 31
Paper selection prompt and criteria at the bottom
Table of contents with paper titles:
QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery Authors: Xuan-Bac Nguyen, Hoang-Quan Nguyen, Sankalp Pandey, Tim Faltermeier, Nicholas Borys, Hugh Churchill, Khoa Luu
AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games Authors: Lance Ying, Ryan Truong, Prafull Sharma, Kaiya Ivy Zhao, Nathan Cloos, Kelsey R. Allen, Thomas L. Griffiths, Katherine M. Collins, Jos'e Hern'andez-Orallo, Phillip Isola, Samuel J. Gershman, Joshua B. Tenenbaum
Xray-Visual Models: Scaling Vision models on Industry Scale Data Authors: Shlok Mishra, Tsung-Yu Lin, Linda Wang, Hongli Xu, Yimin Liu, Michael Hsu, Chaitanya Ahuja, Hao Yuan, Jianpeng Cheng, Hong-You Chen, Haoyuan Xu, Chao Li, Abhijeet Awasthi, Jihye Moon, Don Husa, Michael Ge, Sumedha Singla, Arkabandhu Chowdhury, Phong Dingh, Satya Narayan Shukla, Yonghuan Yang, David Jacobs, Qi Guo, Jun Xiao, Xiangjun Fan, Aashu Singh
Selective Training for Large Vision Language Models via Visual Information Gain Authors: Seulbi Lee, Sangheum Hwang
EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models Authors: Yahong Wang, Juncheng Wu, Zhangkai Ni, Chengmei Yang, Yihang Liu, Longzhen Yang, Yuyin Zhou, Ying Wen, Lianghua He
Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents Authors: Haiyang Xu, Xi Zhang, Haowei Liu, Junyang Wang, Zhaozai Zhu, Shengjie Zhou, Xuhao Hu, Feiyu Gao, Junjie Cao, Zihua Wang, Zhiyuan Chen, Jitong Liao, Qi Zheng, Jiahui Zeng, Ze Xu, Shuai Bai, Junyang Lin, Jingren Zhou, Ming Yan
RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward Authors: Qiucheng Wu, Jing Shi, Simon Jenni, Kushal Kafle, Tianyu Wang, Shiyu Chang, Handong Zhao
NRGS-SLAM: Monocular Non-Rigid SLAM for Endoscopy via Deformation-Aware 3D Gaussian Splatting Authors: Jiwei Shan, Zeyu Cai, Yirui Li, Yongbo Chen, Lijun Han, Yun-hui Liu, Hesheng Wang, Shing Shin Cheng
Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery Authors: Jowaria Khan, Anindya Sarkar, Yevgeniy Vorobeychik, Elizabeth Bondi-Kelly
SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery Authors: Lorenzo Caselli, Marco Mistretta, Simone Magistri, Andrew D. Bagdanov
Visual Model Checking: Graph-Based Inference of Visual Routines for Image Retrieval Authors: Adri`a Molina, Oriol Ramos Terrades, Josep Llad'os
IntRec: Intent-based Retrieval with Contrastive Refinement Authors: Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Yue Lu
Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection Authors: Yichen Lu, Siwei Nie, Minlong Lu, Xudong Yang, Xiaobo Zhang, Peng Zhang
Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling Authors: Divyam Madaan, Sumit Chopra, Kyunghyun Cho
LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs Authors: Behzad Bozorgtabar, Dwarikanath Mahapatra, Sudipta Roy, Muzammal Naseer, Imran Razzak, Zongyuan Ge
EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models Authors: Xiaomeng Peng, Xilang Huang, Seon Han Choi
EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection Authors: Hung Mai, Loi Dinh, Duc Hai Nguyen, Dat Do, Luong Doan, Khanh Nguyen Quoc, Huan Vu, Phong Ho, Naeem Ul Islam, Tuan Do
Amber-Image: Efficient Compression of Large-Scale Diffusion Transformers Authors: Chaojie Yang, Tian Li, Yue Zhang, Jun Gao
DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers Authors: Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde
BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning Authors: Siyuan Liang, Yongcheng Jing, Yingjie Wang, Jiaxing Huang, Ee-chien Chang, Dacheng Tao
Attachment Anchors: A Novel Framework for Laparoscopic Grasping Point Prediction in Colorectal Surgery Authors: Dennis N. Schneider, Lars Wagner, Daniel Rueckert, Dirk Wilhelm
Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment Authors: Ivan Rinaldi, Matteo Mendula, Nicola Fanelli, Florence Lev'e, Matteo Testi, Giovanna Castellano, Gennaro Vessio
StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection Authors: Joongwon Chae, Lihui Luo, Yang Liu, Runming Wang, Dongmei Yu, Zeming Liang, Xi Yuan, Dayan Zhang, Zhenglin Chen, Peiwu Qin, Ilmoon Chae
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation Authors: Mubashara Akhtar, Anka Reuel, Prajna Soni, Sanchit Ahuja, Pawan Sasanka Ammanamanchi, Ruchit Rawal, Vil'em Zouhar, Srishti Yadav, Chenxi Whitehouse, Dayeon Ki, Jennifer Mickel, Leshem Choshen, Marek \v{S}uppa, Jan Batzner, Jenny Chim, Jeba Sania, Yanan Long, Hossein A. Rahmani, Christina Knight, Yiyang Nan, Jyoutir Raj, Yu Fan, Shubham Singh, Subramanyam Sahoo, Eliya Habba, Usman Gohar, Siddhesh Pawar, Robert Scholz, Arjun Subramonian, Jingwei Ni, Mykel Kochenderfer, Sanmi Koyejo, Mrinmaya Sachan, Stella Biderman, Zeerak Talat, Avijit Ghosh, Irene Solaiman
Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap) Authors: Xiangyu Zhou, Chenhan Xiao, Yang Weng
Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature Authors: Angelo Porrello, Pietro Buzzega, Felix Dangel, Thomas Sommariva, Riccardo Salami, Lorenzo Bonicelli, Simone Calderara
FoundationPose-Initialized 3D-2D Liver Registration for Surgical Augmented Reality Authors: Hanyuan Zhang, Lucas He, Runlong He, Abdolrahim Kadkhodamohammadi, Danail Stoyanov, Brian R. Davidson, Evangelos B. Mazomenos, Matthew J. Clarkson
NeuDiff Agent: A Governed AI Workflow for Single-Crystal Neutron Crystallography Authors: Zhongcan Xiao (Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennesse USA), Leyi Zhang (Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennesse USA, Department of Linguistics, University of Illinois Urbana-Champaign, Urbana, Illinois, USA), Guannan Zhang (Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA), Xiaoping Wang (Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennesse USA)
MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions Authors: Hui Min Wong, Philip Heesen, Pascal Janetzky, Martin Bendszus, Stefan Feuerriegel
DRetHTR: Linear-Time Decoder-Only Retentive Network for Handwritten Text Recognition Authors: Changhun Kim, Martin Mayr, Thomas Gorges, Fei Wu, Mathias Seuret, Andreas Maier, Vincent Christlein
KLong: Training LLM Agent for Extremely Long-horizon Tasks Authors: Yue Liu, Zhiyuan Hu, Flood Sung, Jiaheng Zhang, Bryan Hooi
ArXiv ID: 2602.17478 Authors: Xuan-Bac Nguyen, Hoang-Quan Nguyen, Sankalp Pandey, Tim Faltermeier, Nicholas Borys, Hugh Churchill, Khoa Luu
Abstract: Characterizing two-dimensional quantum materials from optical microscopy images is challenging due to the subtle layer-dependent contrast, limited labeled data, and significant variation across laboratories and imaging setups. Existing vision models struggle in this domain since they lack physical priors and cannot generalize to new materials or hardware conditions. This work presents a new physics-aware multimodal framework that addresses these limitations from both the data and model perspectives. We first present Synthia, a physics-based synthetic data generator that simulates realistic optical responses of quantum material flakes under thin-film interference. Synthia produces diverse and high-quality samples, helping reduce the dependence on expert manual annotation. We introduce QMat-Instruct, the first large-scale instruction dataset for quantum materials, comprising multimodal, physics-informed question-answer pairs designed to teach Multimodal Large Language Models (MLLMs) to understand the appearance and thickness of flakes. Then, we propose Physics-Aware Instruction Tuning (QuPAINT), a multimodal architecture that incorporates a Physics-Informed Attention module to fuse visual embeddings with optical priors, enabling more robust and discriminative flake representations. Finally, we establish QF-Bench, a comprehensive benchmark spanning multiple materials, substrates, and imaging settings, offering standardized protocols for fair and reproducible evaluation.
Comment: This paper introduces a physics-aware multimodal framework for quantum material discovery, including a new instruction dataset for MLLMs, a physics-informed attention module, and a new benchmark (QF-Bench). Closely matches criterion 2 (new MLLMs), criterion 3 (new embodied AI benchmark and methods with novel angles), and criterion 4 (vision foundation models and applications). Relevance: 10 Novelty: 9
ArXiv ID: 2602.17594 Authors: Lance Ying, Ryan Truong, Prafull Sharma, Kaiya Ivy Zhao, Nathan Cloos, Kelsey R. Allen, Thomas L. Griffiths, Katherine M. Collins, Jos'e Hern'andez-Orallo, Phillip Isola, Samuel J. Gershman, Joshua B. Tenenbaum
Abstract: Rigorously evaluating machine intelligence against the broad spectrum of human general intelligence has become increasingly important and challenging in this era of rapid technological advance. Conventional AI benchmarks typically assess only narrow capabilities in a limited range of human activity. Most are also static, quickly saturating as developers explicitly or implicitly optimize for them. We propose that a more promising way to evaluate human-like general intelligence in AI systems is through a particularly strong form of general game playing: studying how and how well they play and learn to play \textbf{all conceivable human games}, in comparison to human players with the same level of experience, time, or other resources. We define a "human game" to be a game designed by humans for humans, and argue for the evaluative suitability of this space of all such games people can imagine and enjoy -- the "Multiverse of Human Games". Taking a first step towards this vision, we introduce the AI GameStore, a scalable and open-ended platform that uses LLMs with humans-in-the-loop to synthesize new representative human games, by automatically sourcing and adapting standardized and containerized variants of game environments from popular human digital gaming platforms. As a proof of concept, we generated 100 such games based on the top charts of Apple App Store and Steam, and evaluated seven frontier vision-language models (VLMs) on short episodes of play. The best models achieved less than 10% of the human average score on the majority of the games, and especially struggled with games that challenge world-model learning, memory and planning. We conclude with a set of next steps for building out the AI GameStore as a practical way to measure and drive progress toward human-like general intelligence in machines.
Comment: Matches criterion 3 (embodied AI, new benchmark/simulator). Introduces AI GameStore, a scalable, open-ended evaluation platform for general intelligence using human games, and evaluates VLMs on it. Novel benchmark with surprising empirical results. Relevance: 9 Novelty: 9
ArXiv ID: 2602.16918 Authors: Shlok Mishra, Tsung-Yu Lin, Linda Wang, Hongli Xu, Yimin Liu, Michael Hsu, Chaitanya Ahuja, Hao Yuan, Jianpeng Cheng, Hong-You Chen, Haoyuan Xu, Chao Li, Abhijeet Awasthi, Jihye Moon, Don Husa, Michael Ge, Sumedha Singla, Arkabandhu Chowdhury, Phong Dingh, Satya Narayan Shukla, Yonghuan Yang, David Jacobs, Qi Guo, Jun Xiao, Xiangjun Fan, Aashu Singh
Abstract: We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data. Our model leverages over 15 billion curated image-text pairs and 10 billion video-hashtag pairs from Facebook and Instagram, employing robust data curation pipelines that incorporate balancing and noise suppression strategies to maximize semantic diversity while minimizing label noise. We introduce a three-stage training pipeline that combines self-supervised MAE, semi-supervised hashtag classification, and CLIP-style contrastive learning to jointly optimize image and video modalities. Our architecture builds on a Vision Transformer backbone enhanced with efficient token reorganization (EViT) for improved computational efficiency. Extensive experiments demonstrate that Xray-Visual achieves state-of-the-art performance across diverse benchmarks, including ImageNet for image classification, Kinetics and HMDB51 for video understanding, and MSCOCO for cross-modal retrieval. The model exhibits strong robustness to domain shift and adversarial perturbations. We further demonstrate that integrating large language models as text encoders (LLM2CLIP) significantly enhances retrieval performance and generalization capabilities, particularly in real-world environments. Xray-Visual establishes new benchmarks for scalable, multimodal vision models, while maintaining superior accuracy and computational efficiency.
Comment: Matches criterion 4 (vision foundation models and applications): Presents Xray-Visual, a unified vision model trained on industry-scale data, with a novel training pipeline and integration with LLMs for improved retrieval and generalization. Relevance: 10 Novelty: 8
ArXiv ID: 2602.17186 Authors: Seulbi Lee, Sangheum Hwang
Abstract: Large Vision Language Models (LVLMs) have achieved remarkable progress, yet they often suffer from language bias, producing answers without relying on visual evidence. While prior work attempts to mitigate this issue through decoding strategies, architectural modifications, or curated instruction data, they typically lack a quantitative measure of how much individual training samples or tokens actually benefit from the image. In this work, we introduce Visual Information Gain (VIG), a perplexity-based metric that measures the reduction in prediction uncertainty provided by visual input. VIG enables fine-grained analysis at both sample and token levels, effectively highlighting visually grounded elements such as colors, spatial relations, and attributes. Leveraging this, we propose a VIG-guided selective training scheme that prioritizes high-VIG samples and tokens. This approach improves visual grounding and mitigates language bias, achieving superior performance with significantly reduced supervision by focusing exclusively on visually informative samples and tokens.
Comment: Matches criterion 2 (new VLLMs/MLLMs) and criterion 1 (methodological improvement to spatial understanding in LVLMs via Visual Information Gain for better visual grounding). The paper introduces a new metric (VIG) and a selective training scheme to improve visual grounding and reduce language bias in LVLMs. Relevance: 10 Novelty: 8
ArXiv ID: 2602.17196 Authors: Yahong Wang, Juncheng Wu, Zhangkai Ni, Chengmei Yang, Yihang Liu, Longzhen Yang, Yuyin Zhou, Ying Wen, Lianghua He
Abstract: Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to prune remains largely heuristic. Existing approaches typically rely on static, empirically selected layers, which limit interpretability and transferability across models. In this work, we introduce a matrix-entropy perspective and identify an "Entropy Collapse Layer" (ECL), where the information content of visual representations exhibits a sharp and consistent drop, which provides a principled criterion for selecting the pruning stage. Building on this observation, we propose EntropyPrune, a novel matrix-entropy-guided token pruning framework that quantifies the information value of individual visual tokens and prunes redundant ones without relying on attention maps. Moreover, to enable efficient computation, we exploit the spectral equivalence of dual Gram matrices, reducing the complexity of entropy computation and yielding up to a 64x theoretical speedup. Extensive experiments on diverse multimodal benchmarks demonstrate that EntropyPrune consistently outperforms state-of-the-art pruning methods in both accuracy and efficiency. On LLaVA-1.5-7B, our method achieves a 68.2% reduction in FLOPs while preserving 96.0% of the original performance. Furthermore, EntropyPrune generalizes effectively to high-resolution and video-based models, highlighting the strong robustness and scalability in practical MLLM acceleration. The code will be publicly available at https://github.com/YahongWang1/EntropyPrune.
Comment: This paper introduces EntropyPrune, a matrix-entropy-guided visual token pruning framework for MLLMs, improving efficiency and accuracy. It directly matches criterion 2 (new MLLMs) and criterion 4 (vision foundation models and applications), with a novel statistical trick for token pruning. Relevance: 10 Novelty: 8
ArXiv ID: 2602.16855 Authors: Haiyang Xu, Xi Zhang, Haowei Liu, Junyang Wang, Zhaozai Zhu, Shengjie Zhou, Xuhao Hu, Feiyu Gao, Junjie Cao, Zihua Wang, Zhiyuan Chen, Jitong Liao, Qi Zheng, Jiahui Zeng, Ze Xu, Shuai Bai, Junyang Lin, Jingren Zhou, Ming Yan
Abstract: The paper introduces GUI-Owl-1.5, the latest native GUI agent model that features instruct/thinking variants in multiple sizes (2B/4B/8B/32B/235B) and supports a range of platforms (desktop, mobile, browser, and more) to enable cloud-edge collaboration and real-time interaction. GUI-Owl-1.5 achieves state-of-the-art results on more than 20+ GUI benchmarks on open-source models: (1) on GUI automation tasks, it obtains 56.5 on OSWorld, 71.6 on AndroidWorld, and 48.4 on WebArena; (2) on grounding tasks, it obtains 80.3 on ScreenSpotPro; (3) on tool-calling tasks, it obtains 47.6 on OSWorld-MCP, and 46.8 on MobileWorld; (4) on memory and knowledge tasks, it obtains 75.5 on GUI-Knowledge Bench. GUI-Owl-1.5 incorporates several key innovations: (1) Hybird Data Flywheel: we construct the data pipeline for UI understanding and trajectory generation based on a combination of simulated environments and cloud-based sandbox environments, in order to improve the efficiency and quality of data collection. (2) Unified Enhancement of Agent Capabilities: we use a unified thought-synthesis pipeline to enhance the model's reasoning capabilities, while placing particular emphasis on improving key agent abilities, including Tool/MCP use, memory and multi-agent adaptation; (3) Multi-platform Environment RL Scaling: We propose a new environment RL algorithm, MRPO, to address the challenges of multi-platform conflicts and the low training efficiency of long-horizon tasks. The GUI-Owl-1.5 models are open-sourced, and an online cloud-sandbox demo is available at https://github.com/X-PLUG/MobileAgent.
Comment: Matches criterion 2 (new VLLMs/MLLMs) and criterion 3 (embodied AI, new methods and benchmarks). Introduces GUI-Owl-1.5, a multi-platform GUI agent model with new RL algorithm and simulated environments for UI understanding, and open-sourced models. Relevance: 9 Novelty: 8
ArXiv ID: 2602.17558 Authors: Qiucheng Wu, Jing Shi, Simon Jenni, Kushal Kafle, Tianyu Wang, Shiyu Chang, Handong Zhao
Abstract: Recent advances in multimodal large language models (MLLMs) have shown great potential for extending vision-language reasoning to professional tool-based image editing, enabling intuitive and creative editing. A promising direction is to use reinforcement learning (RL) to enable MLLMs to reason about and execute optimal tool-use plans within professional image-editing software. However, training remains challenging due to the lack of reliable, verifiable reward signals that can reflect the inherently subjective nature of creative editing. In this work, we introduce RetouchIQ, a framework that performs instruction-based executable image editing through MLLM agents guided by a generalist reward model. RetouchIQ interprets user-specified editing intentions and generates corresponding, executable image adjustments, bridging high-level aesthetic goals with precise parameter control. To move beyond conventional, rule-based rewards that compute similarity against a fixed reference image using handcrafted metrics, we propose a generalist reward model, an RL fine-tuned MLLM that evaluates edited results through a set of generated metrics on a case-by-case basis. Then, the reward model provides scalar feedback through multimodal reasoning, enabling reinforcement learning with high-quality, instruction-consistent gradients. We curate an extended dataset with 190k instruction-reasoning pairs and establish a new benchmark for instruction-based image editing. Experiments show that RetouchIQ substantially improves both semantic consistency and perceptual quality over previous MLLM-based and diffusion-based editing systems. Our findings demonstrate the potential of generalist reward-driven MLLM agents as flexible, explainable, and executable assistants for professional image editing.
Comment: Matches criterion 2 (new MLLMs): Introduces RetouchIQ, an MLLM agent for instruction-based image retouching using RL and a generalist reward model. Also relevant to criterion 4 (vision foundation models and applications) as it applies MLLMs to professional image editing. Relevance: 9 Novelty: 8
ArXiv ID: 2602.17182 Authors: Jiwei Shan, Zeyu Cai, Yirui Li, Yongbo Chen, Lijun Han, Yun-hui Liu, Hesheng Wang, Shing Shin Cheng
Abstract: Visual simultaneous localization and mapping (V-SLAM) is a fundamental capability for autonomous perception and navigation. However, endoscopic scenes violate the rigidity assumption due to persistent soft-tissue deformations, creating a strong coupling ambiguity between camera ego-motion and intrinsic deformation. Although recent monocular non-rigid SLAM methods have made notable progress, they often lack effective decoupling mechanisms and rely on sparse or low-fidelity scene representations, which leads to tracking drift and limited reconstruction quality. To address these limitations, we propose NRGS-SLAM, a monocular non-rigid SLAM system for endoscopy based on 3D Gaussian Splatting. To resolve the coupling ambiguity, we introduce a deformation-aware 3D Gaussian map that augments each Gaussian primitive with a learnable deformation probability, optimized via a Bayesian self-supervision strategy without requiring external non-rigidity labels. Building on this representation, we design a deformable tracking module that performs robust coarse-to-fine pose estimation by prioritizing low-deformation regions, followed by efficient per-frame deformation updates. A carefully designed deformable mapping module progressively expands and refines the map, balancing representational capacity and computational efficiency. In addition, a unified robust geometric loss incorporates external geometric priors to mitigate the inherent ill-posedness of monocular non-rigid SLAM. Extensive experiments on multiple public endoscopic datasets demonstrate that NRGS-SLAM achieves more accurate camera pose estimation (up to 50% reduction in RMSE) and higher-quality photo-realistic reconstructions than state-of-the-art methods. Comprehensive ablation studies further validate the effectiveness of our key design choices. Source code will be publicly available upon paper acceptance.
Comment: Matches criterion 1 (spatial understanding on embodied agents) and criterion 3 (new methods for embodied AI, simulator-related). Proposes a new monocular non-rigid SLAM system for endoscopy using 3D Gaussian Splatting and deformation-aware mapping. Relevance: 8 Novelty: 8
ArXiv ID: 2602.17605 Authors: Jowaria Khan, Anindya Sarkar, Yevgeniy Vorobeychik, Elizabeth Bondi-Kelly
Abstract: In many real-world settings, such as environmental monitoring, disaster response, or public health, with costly and difficult data collection and dynamic environments, strategically sampling from unobserved regions is essential for efficiently uncovering hidden targets under tight resource constraints. Yet, sparse and biased geospatial ground truth limits the applicability of existing learning-based methods, such as reinforcement learning. To address this, we propose a unified geospatial discovery framework that integrates active learning, online meta-learning, and concept-guided reasoning. Our approach introduces two key innovations built on a shared notion of concept relevance, which captures how domain-specific factors influence target presence: a concept-weighted uncertainty sampling strategy, where uncertainty is modulated by learned relevance based on readily-available domain-specific concepts (e.g., land cover, source proximity); and a relevance-aware meta-batch formation strategy that promotes semantic diversity during online-meta updates, improving generalization in dynamic environments. Our experiments include testing on a real-world dataset of cancer-causing PFAS (Per- and polyfluoroalkyl substances) contamination, showcasing our method's reliability at uncovering targets with limited data and a varying environment.
Comment: Matches criterion 1 (new methodological improvements to spatial understanding and intelligence, especially for embodied agents in geospatial discovery). Introduces concept-guided active learning and meta-learning for efficient spatial exploration. Relevance: 8 Novelty: 7
ArXiv ID: 2602.17395 Authors: Lorenzo Caselli, Marco Mistretta, Simone Magistri, Andrew D. Bagdanov
Abstract: Generalized Category Discovery (GCD) aims to identify novel categories in unlabeled data while leveraging a small labeled subset of known classes. Training a parametric classifier solely on image features often leads to overfitting to old classes, and recent multimodal approaches improve performance by incorporating textual information. However, they treat modalities independently and incur high computational cost. We propose SpectralGCD, an efficient and effective multimodal approach to GCD that uses CLIP cross-modal image-concept similarities as a unified cross-modal representation. Each image is expressed as a mixture over semantic concepts from a large task-agnostic dictionary, which anchors learning to explicit semantics and reduces reliance on spurious visual cues. To maintain the semantic quality of representations learned by an efficient student, we introduce Spectral Filtering which exploits a cross-modal covariance matrix over the softmaxed similarities measured by a strong teacher model to automatically retain only relevant concepts from the dictionary. Forward and reverse knowledge distillation from the same teacher ensures that the cross-modal representations of the student remain both semantically sufficient and well-aligned. Across six benchmarks, SpectralGCD delivers accuracy comparable to or significantly superior to state-of-the-art methods at a fraction of the computational cost. The code is publicly available at: https://github.com/miccunifi/SpectralGCD.
Comment: Matches criterion 2 (shows new multimodal approach leveraging CLIP for cross-modal representation learning) and criterion 4 (applies vision foundation models, i.e., CLIP, for category discovery). Uses clever spectral filtering and knowledge distillation for efficient multimodal learning. Relevance: 8 Novelty: 7
ArXiv ID: 2602.17386 Authors: Adri`a Molina, Oriol Ramos Terrades, Josep Llad'os
Abstract: Information retrieval lies at the foundation of the modern digital industry. While natural language search has seen dramatic progress in recent years largely driven by embedding-based models and large-scale pretraining, the field still faces significant challenges. Specifically, queries that involve complex relationships, object compositions, or precise constraints such as identities, counts and proportions often remain unresolved or unreliable within current frameworks. In this paper, we propose a novel framework that integrates formal verification into deep learning-based image retrieval through a synergistic combination of graph-based verification methods and neural code generation. Our approach aims to support open-vocabulary natural language queries while producing results that are both trustworthy and verifiable. By grounding retrieval results in a system of formal reasoning, we move beyond the ambiguity and approximation that often characterize vector representations. Instead of accepting uncertainty as a given, our framework explicitly verifies each atomic truth in the user query against the retrieved content. This allows us to not only return matching results, but also to identify and mark which specific constraints are satisfied and which remain unmet, thereby offering a more transparent and accountable retrieval process while boosting the results of the most popular embedding-based approaches.
Comment: Matches criterion 4 (vision foundation models and applications) as it proposes a novel graph-based, verifiable image retrieval framework that integrates formal verification with deep learning, addressing limitations of embedding-based retrieval. Relevance: 7 Novelty: 8
ArXiv ID: 2602.17639 Authors: Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Yue Lu
Abstract: Retrieving user-specified objects from complex scenes remains a challenging task, especially when queries are ambiguous or involve multiple similar objects. Existing open-vocabulary detectors operate in a one-shot manner, lacking the ability to refine predictions based on user feedback. To address this, we propose IntRec, an interactive object retrieval framework that refines predictions based on user feedback. At its core is an Intent State (IS) that maintains dual memory sets for positive anchors (confirmed cues) and negative constraints (rejected hypotheses). A contrastive alignment function ranks candidate objects by maximizing similarity to positive cues while penalizing rejected ones, enabling fine-grained disambiguation in cluttered scenes. Our interactive framework provides substantial improvements in retrieval accuracy without additional supervision. On LVIS, IntRec achieves 35.4 AP, outperforming OVMR, CoDet, and CAKE by +2.3, +3.7, and +0.5, respectively. On the challenging LVIS-Ambiguous benchmark, it improves performance by +7.9 AP over its one-shot baseline after a single corrective feedback, with less than 30 ms of added latency per interaction.
Comment: Matches criterion 1 (methodological improvement to spatial understanding): Proposes IntRec, an interactive object retrieval framework that refines predictions based on user feedback, using intent state and contrastive alignment for spatial disambiguation. Relevance: 8 Novelty: 7
ArXiv ID: 2602.17484 Authors: Yichen Lu, Siwei Nie, Minlong Lu, Xudong Yang, Xiaobo Zhang, Peng Zhang
Abstract: Image Copy Detection (ICD) aims to identify manipulated content between image pairs through robust feature representation learning. While self-supervised learning (SSL) has advanced ICD systems, existing view-level contrastive methods struggle with sophisticated edits due to insufficient fine-grained correspondence learning. We address this limitation by exploiting the inherent geometric traceability in edited content through two key innovations. First, we propose PixTrace - a pixel coordinate tracking module that maintains explicit spatial mappings across editing transformations. Second, we introduce CopyNCE, a geometrically-guided contrastive loss that regularizes patch affinity using overlap ratios derived from PixTrace's verified mappings. Our method bridges pixel-level traceability with patch-level similarity learning, suppressing supervision noise in SSL training. Extensive experiments demonstrate not only state-of-the-art performance (88.7% uAP / 83.9% RP90 for matcher, 72.6% uAP / 68.4% RP90 for descriptor on DISC21 dataset) but also better interpretability over existing methods.
Comment: Matches criterion 1 (methodological improvement to spatial understanding): Proposes PixTrace and CopyNCE for improved spatial correspondence and patch affinity in image copy detection, focusing on geometric traceability and spatial mappings. Relevance: 8 Novelty: 7
ArXiv ID: 2602.16979 Authors: Divyam Madaan, Sumit Chopra, Kyunghyun Cho
Abstract: Despite the recent success of Multimodal Large Language Models (MLLMs), existing approaches predominantly assume the availability of multiple modalities during training and inference. In practice, multimodal data is often incomplete because modalities may be missing, collected asynchronously, or available only for a subset of examples. In this work, we propose PRIMO, a supervised latent-variable imputation model that quantifies the predictive impact of any missing modality within the multimodal learning setting. PRIMO enables the use of all available training examples, whether modalities are complete or partial. Specifically, it models the missing modality through a latent variable that captures its relationship with the observed modality in the context of prediction. During inference, we draw many samples from the learned distribution over the missing modality to both obtain the marginal predictive distribution (for the purpose of prediction) and analyze the impact of the missing modalities on the prediction for each instance. We evaluate PRIMO on a synthetic XOR dataset, Audio-Vision MNIST, and MIMIC-III for mortality and ICD-9 prediction. Across all datasets, PRIMO obtains performance comparable to unimodal baselines when a modality is fully missing and to multimodal baselines when all modalities are available. PRIMO quantifies the predictive impact of a modality at the instance level using a variance-based metric computed from predictions across latent completions. We visually demonstrate how varying completions of the missing modality result in a set of plausible labels.
Comment: Matches criterion 2 (new MLLMs): Proposes PRIMO, a supervised latent-variable imputation model for multimodal learning with missing modalities, and quantifies predictive impact of missing modalities. This is a methodological contribution to MLLMs. Relevance: 8 Novelty: 7
ArXiv ID: 2602.17535 Authors: Behzad Bozorgtabar, Dwarikanath Mahapatra, Sudipta Roy, Muzammal Naseer, Imran Razzak, Zongyuan Ge
Abstract: Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging, but their reliability under domain shift hinges on calibrated uncertainty with guarantees. Split conformal prediction (SCP) offers finite-sample coverage, yet prediction sets often become large (low efficiency) and class-wise coverage unbalanced-high class-conditioned coverage gap (CCV), especially in few-shot, imbalanced regimes; moreover, naively adapting to calibration labels breaks exchangeability and voids guarantees. We propose \texttt{\textbf{LATA}} (Laplacian-Assisted Transductive Adaptation), a \textit{training- and label-free} refinement that operates on the joint calibration and test pool by smoothing zero-shot probabilities over an image-image k-NN graph using a small number of CCCP mean-field updates, preserving SCP validity via a deterministic transform. We further introduce a \textit{failure-aware} conformal score that plugs into the vision-language uncertainty (ViLU) framework, providing instance-level difficulty and label plausibility to improve prediction set efficiency and class-wise balance at fixed coverage. \texttt{\textbf{LATA}} is black-box (no VLM updates), compute-light (windowed transduction, no backprop), and includes an optional prior knob that can run strictly label-free or, if desired, in a label-informed variant using calibration marginals once. Across \textbf{three} medical VLMs and \textbf{nine} downstream tasks, \texttt{\textbf{LATA}} consistently reduces set size and CCV while matching or tightening target coverage, outperforming prior transductive baselines and narrowing the gap to label-using methods, while using far less compute. Comprehensive ablations and qualitative analyses show that \texttt{\textbf{LATA}} sharpens zero-shot predictions without compromising exchangeability.
Comment: This paper proposes LATA, a Laplacian-assisted transductive adaptation method for conformal uncertainty in medical VLMs. It is directly relevant to criterion 4 (vision foundation models and applications), and also touches on uncertainty calibration in VLMs. Relevance: 8 Novelty: 7
ArXiv ID: 2602.17419 Authors: Xiaomeng Peng, Xilang Huang, Seon Han Choi
Abstract: Industrial anomaly detection is important for smart manufacturing, but many deep learning approaches produce only binary decisions and provide limited semantic explanations. Multimodal large language models (MLLMs) can potentially generate fine-grained, language-based analyses, yet existing methods often require costly fine-tuning and do not consistently improve anomaly detection accuracy compared to lightweight specialist detectors. We propose expert-augmented attention guidance for industrial anomaly detection in MLLMs (EAGLE), a tuning-free framework that integrates outputs from expert model to guide MLLMs toward both accurate detection and interpretable anomaly descriptions. We further study how EAGLE affects MLLMs internals by examining the attention distribution of MLLMs to the anomalous image regions in the intermediate layers. We observe that successful anomaly detection is associated with increased attention concentration on anomalous regions, and EAGLE tends to encourage this alignment. Experiments on MVTec-AD and VisA show that EAGLE improves anomaly detection performance across multiple MLLMs without any parameter updates, achieving results comparable to fine-tuning based methods. Code is available at \href{https://github.com/shengtun/Eagle}{https://github.com/shengtun/Eagle}
Comment: This paper proposes EAGLE, a tuning-free framework for industrial anomaly detection using MLLMs, integrating expert model outputs for better detection and interpretability. Closely matches criterion 2 (new MLLMs) and also relates to criterion 4 (vision foundation models and applications). Relevance: 8 Novelty: 7
ArXiv ID: 2602.17260 Authors: Hung Mai, Loi Dinh, Duc Hai Nguyen, Dat Do, Luong Doan, Khanh Nguyen Quoc, Huan Vu, Phong Ho, Naeem Ul Islam, Tuan Do
Abstract: Recent advances in foundation video generators such as Sora2, Veo3, and other commercial systems have produced highly realistic synthetic videos, exposing the limitations of existing detection methods that rely on shallow embedding trajectories, image-based adaptation, or computationally heavy MLLMs. We propose EA-Swin, an Embedding-Agnostic Swin Transformer that models spatiotemporal dependencies directly on pretrained video embeddings via a factorized windowed attention design, making it compatible with generic ViT-style patch-based encoders. Alongside the model, we construct the EA-Video dataset, a benchmark dataset comprising 130K videos that integrates newly collected samples with curated existing datasets, covering diverse commercial and open-source generators and including unseen-generator splits for rigorous cross-distribution evaluation. Extensive experiments show that EA-Swin achieves 0.97-0.99 accuracy across major generators, outperforming prior SoTA methods (typically 0.8-0.9) by a margin of 5-20%, while maintaining strong generalization to unseen distributions, establishing a scalable and robust solution for modern AI-generated video detection.
Comment: Matches criterion 4 (vision foundation models and applications) as it proposes a new Swin Transformer-based method for detecting AI-generated videos, and introduces a new large-scale benchmark dataset. Also relevant to criterion 3 (new benchmark for video detection). Relevance: 7 Novelty: 7
ArXiv ID: 2602.17047 Authors: Chaojie Yang, Tian Li, Yue Zhang, Jun Gao
Abstract: Diffusion Transformer (DiT) architectures have significantly advanced Text-to-Image (T2I) generation but suffer from prohibitive computational costs and deployment barriers. To address these challenges, we propose an efficient compression framework that transforms the 60-layer dual-stream MMDiT-based Qwen-Image into lightweight models without training from scratch. Leveraging this framework, we introduce Amber-Image, a series of streamlined T2I models. We first derive Amber-Image-10B using a timestep-sensitive depth pruning strategy, where retained layers are reinitialized via local weight averaging and optimized through layer-wise distillation and full-parameter fine-tuning. Building on this, we develop Amber-Image-6B by introducing a hybrid-stream architecture that converts deep-layer dual streams into a single stream initialized from the image branch, further refined via progressive distillation and lightweight fine-tuning. Our approach reduces parameters by 70% and eliminates the need for large-scale data engineering. Notably, the entire compression and training pipeline-from the 10B to the 6B variant-requires fewer than 2,000 GPU hours, demonstrating exceptional cost-efficiency compared to training from scratch. Extensive evaluations on benchmarks like DPG-Bench and LongText-Bench show that Amber-Image achieves high-fidelity synthesis and superior text rendering, matching much larger models.
Comment: This paper presents Amber-Image, an efficient compression framework for large-scale diffusion transformers (vision foundation models) for text-to-image generation. It matches criterion 4 (vision foundation models and applications), with a focus on model compression and efficiency. Relevance: 7 Novelty: 7
ArXiv ID: 2602.16968 Authors: Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde
Abstract: Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses constant-sized patches throughout the entire denoising phase, regardless of the content's complexity. We propose dynamic tokenization, an efficient test-time strategy that varies patch sizes based on content complexity and the denoising timestep. Our key insight is that early timesteps only require coarser patches to model global structure, while later iterations demand finer (smaller-sized) patches to refine local details. During inference, our method dynamically reallocates patch sizes across denoising steps for image and video generation and substantially reduces cost while preserving perceptual generation quality. Extensive experiments demonstrate the effectiveness of our approach: it achieves up to $3.52\times$ and $3.2\times$ speedup on FLUX-1.Dev and Wan $2.1$, respectively, without compromising the generation quality and prompt adherence.
Comment: Matches criterion 4 (vision foundation models and their applications). Proposes a new method for efficient inference in Diffusion Transformers, which are widely used in vision foundation models for generative modeling. Relevance: 7 Novelty: 6
ArXiv ID: 2602.17168 Authors: Siyuan Liang, Yongcheng Jing, Yingjie Wang, Jiaxing Huang, Ee-chien Chang, Dacheng Tao
Abstract: Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence. Existing methods often fail under strong detection or continuous fine-tuning, largely due to (1) cross-modal inconsistency that exposes trigger patterns and (2) gradient dilution at low poisoning rates that accelerates backdoor forgetting. These coupled causes remain insufficiently modeled and addressed. We propose BadCLIP++, a unified framework that tackles both challenges. For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions, preserving clean-data statistics while producing compact trigger distributions. We further apply target-aligned subset selection to strengthen signals at low injection rates. For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment, and stabilize model parameters through curvature control and elastic weight consolidation, maintaining solutions within a low-curvature wide basin resistant to fine-tuning. We also provide the first theoretical analysis showing that, within a trust region, gradients from clean fine-tuning and backdoor objectives are co-directional, yielding a non-increasing upper bound on attack success degradation. Experiments demonstrate that with only 0.3% poisoning, BadCLIP++ achieves 99.99% attack success rate (ASR) in digital settings, surpassing baselines by 11.4 points. Across nineteen defenses, ASR remains above 99.90% with less than 0.8% drop in clean accuracy. The method further attains 65.03% success in physical attacks and shows robustness against watermark removal defenses.
Comment: Matches criterion 2 (VLLMs/MLLMs) as it studies backdoor attacks on multimodal contrastive learning models, with new theoretical and empirical insights. Also of interest for clever statistical tricks. Relevance: 6 Novelty: 7
ArXiv ID: 2602.17310 Authors: Dennis N. Schneider, Lars Wagner, Daniel Rueckert, Dirk Wilhelm
Abstract: Accurate grasping point prediction is a key challenge for autonomous tissue manipulation in minimally invasive surgery, particularly in complex and variable procedures such as colorectal interventions. Due to their complexity and prolonged duration, colorectal procedures have been underrepresented in current research. At the same time, they pose a particularly interesting learning environment due to repetitive tissue manipulation, making them a promising entry point for autonomous, machine learning-driven support. Therefore, in this work, we introduce attachment anchors, a structured representation that encodes the local geometric and mechanical relationships between tissue and its anatomical attachments in colorectal surgery. This representation reduces uncertainty in grasping point prediction by normalizing surgical scenes into a consistent local reference frame. We demonstrate that attachment anchors can be predicted from laparoscopic images and incorporated into a grasping framework based on machine learning. Experiments on a dataset of 90 colorectal surgeries demonstrate that attachment anchors improve grasping point prediction compared to image-only baselines. There are particularly strong gains in out-of-distribution settings, including unseen procedures and operating surgeons. These results suggest that attachment anchors are an effective intermediate representation for learning-based tissue manipulation in colorectal surgery.
Comment: Matches criterion 1 (methodological improvements to spatial understanding on embodied agents) as it introduces a new structured representation for grasping point prediction in surgical robotics, with strong out-of-distribution results. Relevance: 6 Novelty: 7
ArXiv ID: 2602.17599 Authors: Ivan Rinaldi, Matteo Mendula, Nicola Fanelli, Florence Lev'e, Matteo Testi, Giovanna Castellano, Gennaro Vessio
Abstract: Music generation has advanced markedly through multimodal deep learning, enabling models to synthesize audio from text and, more recently, from images. However, existing image-conditioned systems suffer from two fundamental limitations: (i) they are typically trained on natural photographs, limiting their ability to capture the richer semantic, stylistic, and cultural content of artworks; and (ii) most rely on an image-to-text conversion stage, using language as a semantic shortcut that simplifies conditioning but prevents direct visual-to-audio learning. Motivated by these gaps, we introduce ArtSound, a large-scale multimodal dataset of 105,884 artwork-music pairs enriched with dual-modality captions, obtained by extending ArtGraph and the Free Music Archive. We further propose ArtToMus, the first framework explicitly designed for direct artwork-to-music generation, which maps digitized artworks to music without image-to-text translation or language-based semantic supervision. The framework projects visual embeddings into the conditioning space of a latent diffusion model, enabling music synthesis guided solely by visual information. Experimental results show that ArtToMus generates musically coherent and stylistically consistent outputs that reflect salient visual cues of the source artworks. While absolute alignment scores remain lower than those of text-conditioned systems-as expected given the substantially increased difficulty of removing linguistic supervision-ArtToMus achieves competitive perceptual quality and meaningful cross-modal correspondence. This work establishes direct visual-to-music generation as a distinct and challenging research direction, and provides resources that support applications in multimedia art, cultural heritage, and AI-assisted creative practice. Code and dataset will be publicly released upon acceptance.
Comment: This paper presents a new framework for direct artwork-to-music generation using visual conditioning and a large-scale multimodal dataset. It is a novel multimodal generative model, but not a VLLM/MLLM in the sense of vision-language models, nor does it focus on spatial intelligence or embodied AI. Closest to criterion 2 (new MLLMs), but the modality is vision-to-audio. Relevance: 5 Novelty: 8
ArXiv ID: 2602.17048 Authors: Joongwon Chae, Lihui Luo, Yang Liu, Runming Wang, Dongmei Yu, Zeming Liang, Xi Yuan, Dayan Zhang, Zhenglin Chen, Peiwu Qin, Ilmoon Chae
Abstract: Max pooling is the de facto standard for converting anomaly score maps into image-level decisions in memory-bank-based unsupervised anomaly detection (UAD). However, because it relies on a single extreme response, it discards most information about how anomaly evidence is distributed and structured across the image, often causing normal and anomalous scores to overlap. We propose StructCore, a training-free, structure-aware image-level scoring method that goes beyond max pooling. Given an anomaly score map, StructCore computes a low-dimensional structural descriptor phi(S) that captures distributional and spatial characteristics, and refines image-level scoring via a diagonal Mahalanobis calibration estimated from train-good samples, without modifying pixel-level localization. StructCore achieves image-level AUROC scores of 99.6% on MVTec AD and 98.4% on VisA, demonstrating robust image-level anomaly detection by exploiting structural signatures missed by max pooling.
Comment: Matches criterion 4 (vision foundation models and applications) as it proposes a new structure-aware scoring method for unsupervised anomaly detection, improving over max pooling. Relevance: 6 Novelty: 6
ArXiv ID: 2602.16763 Authors: Mubashara Akhtar, Anka Reuel, Prajna Soni, Sanchit Ahuja, Pawan Sasanka Ammanamanchi, Ruchit Rawal, Vil'em Zouhar, Srishti Yadav, Chenxi Whitehouse, Dayeon Ki, Jennifer Mickel, Leshem Choshen, Marek \v{S}uppa, Jan Batzner, Jenny Chim, Jeba Sania, Yanan Long, Hossein A. Rahmani, Christina Knight, Yiyang Nan, Jyoutir Raj, Yu Fan, Shubham Singh, Subramanyam Sahoo, Eliya Habba, Usman Gohar, Siddhesh Pawar, Robert Scholz, Arjun Subramonian, Jingwei Ni, Mykel Kochenderfer, Sanmi Koyejo, Mrinmaya Sachan, Stella Biderman, Zeerak Talat, Avijit Ghosh, Irene Solaiman
Abstract: Artificial Intelligence (AI) benchmarks play a central role in measuring progress in model development and guiding deployment decisions. However, many benchmarks quickly become saturated, meaning that they can no longer differentiate between the best-performing models, diminishing their long-term value. In this study, we analyze benchmark saturation across 60 Large Language Model (LLM) benchmarks selected from technical reports by major model developers. To identify factors driving saturation, we characterize benchmarks along 14 properties spanning task design, data construction, and evaluation format. We test five hypotheses examining how each property contributes to saturation rates. Our analysis reveals that nearly half of the benchmarks exhibit saturation, with rates increasing as benchmarks age. Notably, hiding test data (i.e., public vs. private) shows no protective effect, while expert-curated benchmarks resist saturation better than crowdsourced ones. Our findings highlight which design choices extend benchmark longevity and inform strategies for more durable evaluation.
Comment: Matches criterion 3 (embodied AI, new benchmark): Systematic study of benchmark saturation in AI, with insights into benchmark design and longevity. While not simulator-specific, it is highly relevant to benchmarking in AI. Relevance: 6 Novelty: 6
ArXiv ID: 2602.17107 Authors: Xiangyu Zhou, Chenhan Xiao, Yang Weng
Abstract: Shapley value-based methods have become foundational in explainable artificial intelligence (XAI), offering theoretically grounded feature attributions through cooperative game theory. However, in practice, particularly in vision tasks, the assumption of feature independence breaks down, as features (i.e., pixels) often exhibit strong spatial and semantic dependencies. To address this, modern SHAP implementations now include the Owen value, a hierarchical generalization of the Shapley value that supports group attributions. While the Owen value preserves the foundations of Shapley values, its effectiveness critically depends on how feature groups are defined. We show that commonly used segmentations (e.g., axis-aligned or SLIC) violate key consistency properties, and propose a new segmentation approach that satisfies the $T$-property to ensure semantic alignment across hierarchy levels. This hierarchy enables computational pruning while improving attribution accuracy and interpretability. Experiments on image and tabular datasets demonstrate that O-Shap outperforms baseline SHAP variants in attribution precision, semantic coherence, and runtime efficiency, especially when structure matters.
Comment: This paper proposes O-Shap, a new Owen-based SHAP method for explainable AI, especially in vision tasks. It is relevant to vision foundation models and their interpretability (criterion 4), but not directly about VLLMs/MLLMs or embodied AI. Relevance: 5 Novelty: 7
ArXiv ID: 2602.17385 Authors: Angelo Porrello, Pietro Buzzega, Felix Dangel, Thomas Sommariva, Riccardo Salami, Lorenzo Bonicelli, Simone Calderara
Abstract: Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task interference, causing representation drift and degraded performance. Representation drift regularization provides a natural remedy to disentangle task vectors; however, existing approaches typically require external task data, conflicting with modularity and data availability constraints (e.g., privacy requirements). We propose a dataless approach by framing regularization against representation drift as a curvature matrix approximation problem. This allows us to leverage well-established techniques; in particular, we adopt Kronecker-Factored Approximate Curvature and obtain a practical regularizer that achieves state-of-the-art results in task addition and negation. Our method has constant complexity in the number of tasks and promotes robustness to task vector rescaling, eliminating the need for held-out tuning.
Comment: Somewhat relevant to criterion 4 (vision foundation models): Proposes a dataless regularization method for task arithmetic in foundation models, but not directly about spatial intelligence or VLLMs/MLLMs. Relevance: 5 Novelty: 6
ArXiv ID: 2602.17517 Authors: Hanyuan Zhang, Lucas He, Runlong He, Abdolrahim Kadkhodamohammadi, Danail Stoyanov, Brian R. Davidson, Evangelos B. Mazomenos, Matthew J. Clarkson
Abstract: Augmented reality can improve tumor localization in laparoscopic liver surgery. Existing registration pipelines typically depend on organ contours; deformable (non-rigid) alignment is often handled with finite-element (FE) models coupled to dimensionality-reduction or machine-learning components. We integrate laparoscopic depth maps with a foundation pose estimator for camera-liver pose estimation and replace FE-based deformation with non-rigid iterative closest point (NICP) to lower engineering/modeling complexity and expertise requirements. On real patient data, the depth-augmented foundation pose approach achieved 9.91 mm mean registration error in 3 cases. Combined rigid-NICP registration outperformed rigid-only registration, demonstrating NICP as an efficient substitute for finite-element deformable models. This pipeline achieves clinically relevant accuracy while offering a lightweight, engineering-friendly alternative to FE-based deformation.
Comment: Matches criterion 4 (vision foundation models and applications) as it uses a foundation pose estimator for surgical AR, but is a more incremental application of existing models. Relevance: 5 Novelty: 5
ArXiv ID: 2602.16812 Authors: Zhongcan Xiao (Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennesse USA), Leyi Zhang (Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennesse USA, Department of Linguistics, University of Illinois Urbana-Champaign, Urbana, Illinois, USA), Guannan Zhang (Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA), Xiaoping Wang (Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennesse USA)
Abstract: Large-scale facilities increasingly face analysis and reporting latency as the limiting step in scientific throughput, particularly for structurally and magnetically complex samples that require iterative reduction, integration, refinement, and validation. To improve time-to-result and analysis efficiency, NeuDiff Agent is introduced as a governed, tool-using AI workflow for TOPAZ at the Spallation Neutron Source that takes instrument data products through reduction, integration, refinement, and validation to a validated crystal structure and a publication-ready CIF. NeuDiff Agent executes this established pipeline under explicit governance by restricting actions to allowlisted tools, enforcing fail-closed verification gates at key workflow boundaries, and capturing complete provenance for inspection, auditing, and controlled replay. Performance is assessed using a fixed prompt protocol and repeated end-to-end runs with two large language model backends, with user and machine time partitioned and intervention burden and recovery behaviors quantified under gating. In a reference-case benchmark, NeuDiff Agent reduces wall time from 435 minutes (manual) to 86.5(4.7) to 94.4(3.5) minutes (4.6-5.0x faster) while producing a validated CIF with no checkCIF level A or B alerts. These results establish a practical route to deploy agentic AI in facility crystallography while preserving traceability and publication-facing validation requirements.
Comment: Somewhat relevant to criterion 3 (embodied AI, new benchmark/method): Introduces NeuDiff Agent, an agentic AI workflow for neutron crystallography, with benchmarking and workflow governance. However, the domain is scientific workflow automation, not classic embodied AI or spatial intelligence. Relevance: 4 Novelty: 6
ArXiv ID: 2602.17308 Authors: Hui Min Wong, Philip Heesen, Pascal Janetzky, Martin Bendszus, Stefan Feuerriegel
Abstract: Large language models (LLMs) are increasingly used for diagnostic tasks in medicine. In clinical practice, the correct diagnosis can rarely be immediately inferred from the initial patient presentation alone. Rather, reaching a diagnosis often involves systematic history taking, during which clinicians reason over multiple potential conditions through iterative questioning to resolve uncertainty. This process requires considering differential diagnoses and actively excluding emergencies that demand immediate intervention. Yet, the ability of medical LLMs to generate informative follow-up questions and thus reason over differential diagnoses remains underexplored. Here, we introduce MedClarify, an AI agent for information-seeking that can generate follow-up questions for iterative reasoning to support diagnostic decision-making. Specifically, MedClarify computes a list of candidate diagnoses analogous to a differential diagnosis, and then proactively generates follow-up questions aimed at reducing diagnostic uncertainty. By selecting the question with the highest expected information gain, MedClarify enables targeted, uncertainty-aware reasoning to improve diagnostic performance. In our experiments, we first demonstrate the limitations of current LLMs in medical reasoning, which often yield multiple, similarly likely diagnoses, especially when patient cases are incomplete or relevant information for diagnosis is missing. We then show that our information-theoretic reasoning approach can generate effective follow-up questioning and thereby reduces diagnostic errors by ~27 percentage points (p.p.) compared to a standard single-shot LLM baseline. Altogether, MedClarify offers a path to improve medical LLMs through agentic information-seeking and to thus promote effective dialogues with medical LLMs that reflect the iterative and uncertain nature of real-world clinical reasoning.
Comment: This paper presents MedClarify, an LLM-based agent for medical diagnosis that generates follow-up questions to reduce diagnostic uncertainty. It is an agentic LLM but not focused on spatial intelligence, vision, or multimodal learning. Relevance: 3 Novelty: 6
ArXiv ID: 2602.17387 Authors: Changhun Kim, Martin Mayr, Thomas Gorges, Fei Wu, Mathias Seuret, Andreas Maier, Vincent Christlein
Abstract: State-of-the-art handwritten text recognition (HTR) systems commonly use Transformers, whose growing key-value (KV) cache makes decoding slow and memory-intensive. We introduce DRetHTR, a decoder-only model built on Retentive Networks (RetNet). Compared to an equally sized decoder-only Transformer baseline, DRetHTR delivers 1.6-1.9x faster inference with 38-42% less memory usage, without loss of accuracy. By replacing softmax attention with softmax-free retention and injecting multi-scale sequential priors, DRetHTR avoids a growing KV cache: decoding is linear in output length in both time and memory. To recover the local-to-global inductive bias of attention, we propose layer-wise gamma scaling, which progressively enlarges the effective retention horizon in deeper layers. This encourages early layers to model short-range dependencies and later layers to capture broader context, mitigating the flexibility gap introduced by removing softmax. Consequently, DRetHTR achieves best reported test character error rates of 2.26% (IAM-A, en), 1.81% (RIMES, fr), and 3.46% (Bentham, en), and is competitive on READ-2016 (de) with 4.21%. This demonstrates that decoder-only RetNet enables Transformer-level HTR accuracy with substantially improved decoding speed and memory efficiency.
Comment: This paper introduces a new decoder-only Retentive Network for handwritten text recognition, focusing on efficiency and accuracy. It is a vision model but not multimodal, not about spatial intelligence, embodied AI, or VLLMs/MLLMs. Relevance: 3 Novelty: 6
ArXiv ID: 2602.17547 Authors: Yue Liu, Zhiyuan Hu, Flood Sung, Jiaheng Zhang, Bryan Hooi
Abstract: This paper introduces KLong, an open-source LLM agent trained to solve extremely long-horizon tasks. The principle is to first cold-start the model via trajectory-splitting SFT, then scale it via progressive RL training. Specifically, we first activate basic agentic abilities of a base model with a comprehensive SFT recipe. Then, we introduce Research-Factory, an automated pipeline that generates high-quality training data by collecting research papers and constructing evaluation rubrics. Using this pipeline, we build thousands of long-horizon trajectories distilled from Claude 4.5 Sonnet (Thinking). To train with these extremely long trajectories, we propose a new trajectory-splitting SFT, which preserves early context, progressively truncates later context, and maintains overlap between sub-trajectories. In addition, to further improve long-horizon task-solving capability, we propose a novel progressive RL, which schedules training into multiple stages with progressively extended timeouts. Experiments demonstrate the superiority and generalization of KLong, as shown in Figure 1. Notably, our proposed KLong (106B) surpasses Kimi K2 Thinking (1T) by 11.28% on PaperBench, and the performance improvement generalizes to other coding benchmarks like SWE-bench Verified and MLE-bench.
Comment: This paper introduces a new LLM agent for extremely long-horizon tasks, focusing on agentic abilities and progressive RL. While it is about agentic LLMs, it does not focus on spatial intelligence, embodied agents, or vision/multimodal models. No criteria match closely. Relevance: 3 Novelty: 6
In suggesting papers to your friend, remember that he enjoys papers on computer vision and machine learning, and generative modeling in multi-modal learning. Your friend also likes learning about surprising empirical or insightful results in vision-language models or embodied AI, as well as clever statistical tricks.